import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.textual content import CountVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
# Step 2: Pattern dataset
information = {
‘textual content’: [
‘Congratulations! You have won a free iPhone!’,
‘Important update about your bank account’,
‘Let’s meet for coffee tomorrow?’,
‘WINNER! Claim your prize now’,
‘Can you send me the report?’,
‘Earn money quickly from home’,
‘Lunch at 1 PM?’,
‘You have been selected for a reward’,
],
‘label’: [1, 1, 0, 1, 0, 1, 0, 1] # 1 = spam, 0 = not spam
}
df = pd.DataFrame(information)
# Step 3: Convert textual content to numeric options
vectorizer = CountVectorizer()
X = vectorizer.fit_transform(df[‘text’]) # Bag of phrases mannequin
y = df[‘label’]
# Step 4: Cut up information into coaching and testing units
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.3, random_state=42
)
# Step 5: Prepare the logistic regression mannequin
mannequin = LogisticRegression()
mannequin.match(X_train, y_train)
# Step 6: Make predictions
y_pred = mannequin.predict(X_test)
# Step 7: Consider the mannequin
accuracy = accuracy_score(y_test, y_pred)
print(“Accuracy:”, accuracy)
# Step 8: Take a look at on a customized e mail
pattern = [“Don’t miss out on this limited offer!”]
sample_features = vectorizer.rework(pattern)
prediction = mannequin.predict(sample_features)
print(“Prediction (1=Spam, 0=Not Spam):”, prediction[0])
